CN120389511A - A wind farm equipment modeling and operation and maintenance control method and device based on digital twin - Google Patents
A wind farm equipment modeling and operation and maintenance control method and device based on digital twinInfo
- Publication number
- CN120389511A CN120389511A CN202510467941.4A CN202510467941A CN120389511A CN 120389511 A CN120389511 A CN 120389511A CN 202510467941 A CN202510467941 A CN 202510467941A CN 120389511 A CN120389511 A CN 120389511A
- Authority
- CN
- China
- Prior art keywords
- wind
- model
- data
- wind turbine
- maintenance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Landscapes
- Wind Motors (AREA)
Abstract
本申请提供一种基于数字孪生的风电场设备建模与运维管控方法、装置，通过高精度数字孪生模型构建：基于1:1三维建模技术还原风机实体，集成多源数据，包括设备传感器、视频监控、GIS地形数据，实现物理场与虚拟场的实时映射。智能决策支持模块：利用动态边界层模型预测风资源分布，结合虚拟惯量模拟技术优化并网控制策略，实现新能源波动场景下的电网暂态稳定性保障。全生命周期管理平台：支持从选址规划、运行监控到故障诊断的全流程管理，通过三维可视化大屏实现多业务数据融合展示与交互式运维策略验证。
The present application provides a method and device for modeling and operation and maintenance management of wind farm equipment based on digital twins, which is constructed through a high-precision digital twin model: based on 1:1 three-dimensional modeling technology to restore the wind turbine entity, integrate multi-source data, including equipment sensors, video monitoring, and GIS terrain data, to achieve real-time mapping of physical fields and virtual fields. Intelligent decision support module: Utilizes a dynamic boundary layer model to predict wind resource distribution, combines virtual inertia simulation technology to optimize grid-connected control strategies, and achieves transient stability assurance of the power grid under new energy fluctuation scenarios. Full life cycle management platform: supports full-process management from site selection planning, operation monitoring to fault diagnosis, and realizes multi-business data fusion display and interactive operation and maintenance strategy verification through a three-dimensional visualization large screen.
Description
Technical Field
The application relates to the technical field of operation and maintenance of wind turbines, in particular to a method and a device for modeling and operation and maintenance control of wind farm equipment based on digital twinning.
Background
Wind power is one of the most potential renewable energy sources in the future, the whole life cycle of the vertical wind power plant is prolonged, the operation and maintenance cost accounts for 25% -30% of the operation cost, and how to effectively reduce the operation and maintenance cost is the key point of operation attention. The problems that 1) a wind farm is located in a remote area mostly, equipment is difficult to maintain after faults occur, 2) equipment maintenance is greatly influenced by uncontrollable natural factors such as wind power and the like, 3) the false alarm rate is too high due to single sensor data, and the problems of insufficient sensor and data quantity, more false alarm and missing report, limited accuracy and the like exist in a predictive maintenance system realized by traditional single data modeling currently exist. 4) The traditional mechanism model is difficult to characterize equipment degradation under complex working conditions. 5) The existing predictive maintenance system response delay exceeds 4 hours.
The digital twin technology is a real-time accurate virtual model of a physical entity in a virtual information space, has the characteristic of virtual-real-time mapping, and can execute monitoring, simulation, prediction and optimization by carrying out multi-dimension/multi-field modeling on the physical entity. Digital twinning is applied in the aerospace field at the earliest, and is gradually expanded to various fields such as industry, folk life and the like. The digital twin technology is introduced into the wind power industry, and powerful support is provided for intelligent operation and maintenance of the wind turbine generator set in a complex scene.
At present, the intelligent operation and digitization level of the wind turbine generator in a complex scene is low, manual intervention is usually required when faults occur, the traditional post-maintenance and periodic maintenance modes are increasingly exposed to limitations, and the maintenance cost is high, so that the wind turbine generator is focused and valued. Therefore, the full life cycle management platform is constructed, and the full flow management from site selection planning, operation monitoring and fault diagnosis is realized, so that the dynamic response of the fan under the complex working condition is accurately simulated, and the full life cycle management platform is the content of important research by the person skilled in the art.
Disclosure of Invention
In view of the foregoing, it is necessary to provide a method and a device for modeling and operation and maintenance control of wind farm equipment based on digital twinning, which utilize a mode feature fusion strategy (clinical+image group chemistry+biochemical index) to protect the maintenance and management level of the equipment. Based on the integrated learning light model, both performance and interpretability are considered.
In a first aspect, an embodiment of the present application provides a method for modeling and controlling operation and maintenance of wind farm equipment based on digital twinning, the method comprising:
Restoring a fan entity based on a 1:1 three-dimensional modeling technology, integrating multi-source data to realize real-time mapping of a physical field and a virtual field, and constructing a high-precision digital twin model, wherein the multi-source data comprises equipment sensors, video monitoring and GIS topography;
Predicting wind resource distribution by utilizing a dynamic boundary layer model, optimizing a grid-connected control strategy by combining a virtual inertia simulation technology, and carrying out intelligent decision support to ensure the transient stability of the power grid under a new energy fluctuation scene;
and constructing a full life cycle management platform, and realizing multi-service data fusion display and interactive operation and maintenance strategy verification through a three-dimensional visual large screen from site selection planning, operation monitoring and full flow management of fault diagnosis.
Optionally, in an implementation manner of the first aspect of the present invention, the 1:1 three-dimensional modeling technology-based fan entity restoration is integrated with multi-source data to realize real-time mapping of a physical field and a virtual field, and a digital twin model of the high-precision wind turbine generator is constructed, wherein the digital twin model comprises four parts, namely, construction of a geometric model, construction of a mechanism model, construction of a data model and construction of a knowledge model;
the construction of the geometric model comprises the steps of constructing a three-dimensional geometric model of a 1:1 wind turbine by three-dimensional modeling software and field measurement data, and restoring the three-dimensional space environment of a real wind turbine by three-dimensional surface information of a blade, a tower and a gear box part to realize high-precision geometric modeling;
The construction of the mechanism model comprises the steps of simulating mechanical behaviors of a blade and a tower by using a finite element analysis model, establishing a thermodynamic model and a vibration model of the wind turbine based on energy conservation and momentum conservation laws, constructing a control strategy based on a physical mechanism, including a wake effect model and a variable pitch control strategy, so as to optimize the power generation efficiency, establishing an electrical system, a mechanical structure and an aerodynamic model of the wind turbine, and simulating the running state and dynamic response of the wind turbine;
The data model is constructed by acquiring key parameters of wind speed, wind direction, power and temperature in real time through an S C A D A system and a state monitoring system, and inputting the key parameters into the model for dynamic simulation;
The knowledge model is constructed by establishing a knowledge graph of the relation between the running state and the fault of the wind turbine, and carrying out intelligent prediction and fault diagnosis on the running state of the wind turbine by combining a machine learning algorithm.
Optionally, in an implementation manner of the first aspect of the present invention, the constructing a digital twin model of a high-precision wind turbine further includes:
From the system dimension of the wind power plant, the operation requirement is disassembled into six important dimensions of man, machine, material, method, ring and measurement, the digital twin body is constructed for the environment, equipment, personnel and management flow, and the operation and the scheduling of loading, cooperation and fusion are carried out on the multiple twin bodies through digital threads, so that the actual business requirement of the operation and the maintenance of the wind power plant is reflected to the greatest extent, and the comprehensive digital management of the wind power plant is realized;
by constructing a three-dimensional model of the wind field environment based on the IF C standard and an internal power generation process of a fan system, organically combining the 3D GIS, BIM information and the fan C A D model, and establishing comprehensive production perceptibility in a virtual space;
based on the comprehensive analysis of the fan design data, the operation and maintenance data and the fault mode, adopting a targeted twin body modeling method for different components,
The state monitoring, fault prediction and simulation deduction of the generator winding are completed through the constructed hybrid model, and the self-learning and continuous optimization of the model structure and parameters can be performed by utilizing the operation data collected in real time.
Optionally, in an implementation manner of the first aspect of the present invention, the predicting wind resource distribution by using a dynamic boundary layer model and optimizing a grid-connected control strategy by combining a virtual inertia simulation technology, performing intelligent decision support, and implementing power grid transient stability guarantee under a new energy fluctuation scene includes:
constructing a dynamic boundary layer model through input data, wherein the input data comprises topographic data, meteorological data and thermodynamic data;
According to the space-time evolution of wind speed in the description atmosphere boundary layer, a momentum equation is constructed, and the formula is as follows:
u i、uj denotes the wind speed component, x i、xj denotes the component of the corresponding parameter, i, j=1, 2,3, ρ denotes the air density, p denotes the air pressure, f c denotes the coriolis parameter, τ ij denotes the reynolds stress, S i denotes the source term, ζ ijk denotes the complete antisymmetric tensor;
Predicting the space-time distribution characteristic of wind resources according to the dynamic boundary layer model;
according to the virtual inertia compensation target, the grid-connected control strategy is optimized by combining the virtual inertia simulation technology, the virtual inertia is optimally distributed, the stable power grid frequency is maintained, and the virtual inertia compensation target formula is as follows:
Wherein, H rcof,HΔf represents critical virtual inertia obtained under different constraint conditions, S gi represents rated capacity of the ith wind turbine generator, S wfj represents rated capacity of the jth generator wind farm, H gi represents inertia of the ith wind turbine generator, m represents number of wind turbine generator, and n represents number of wind farms with virtual inertia.
Optionally, in an implementation manner of the first aspect of the present invention, the optimizing allocation of the virtual inertia to maintain the stability of the grid frequency includes:
Adopting a self-adaptive control algorithm to realize accurate control and smooth adjustment of the output power of the wind power plant;
wherein, the self-adaptive rule is as follows:
Monitoring the running state data of the wind turbine, comparing the running state data with a preset threshold value, starting virtual inertia to control when the deviation exceeds the data range of the threshold value, the method comprises the steps of adjusting the rotating speed or power output of a wind turbine generator, providing additional inertial support for a power grid, slowing down the speed of frequency change, and striving for time for frequency modulation measures, wherein the running state data comprise working frequency and fan rotating speed;
Setting a virtual inertia control time threshold, and stopping controlling the virtual inertia when the running state data of the wind turbine generator is recovered, or stopping controlling the virtual inertia when the control time reaches the control time threshold.
Optionally, in an implementation manner of the first aspect of the present invention, the constructing a full life cycle management platform, the full flow management from site planning, operation monitoring to fault diagnosis includes:
Through the whole life cycle of the wind power plant equipment, mapping the whole flow from site selection planning and operation monitoring to fault diagnosis is carried out by a digital twin technology, the overall layout of the wind power plant and the monitoring of the equipment state are carried out by a three-dimensional visual platform, and the site selection planning and construction scheme is optimized;
and by combining GIS and BIM technologies, the geographic information and equipment information of the wind power plant are integrally managed, so that the whole flow digital management and control from site selection to operation and maintenance is realized.
Optionally, in an implementation manner of the first aspect of the present invention, the implementing multi-service data fusion display and interactive operation and maintenance policy verification through the three-dimensional visual large screen includes:
The three-dimensional visual large screen is used for displaying key indexes of the generated energy, the power and the wind speed of the wind turbine generator in real time, and combining an unmanned aerial vehicle oblique photography technology, dynamically feeding back the health condition of the blade, and carrying out fusion analysis of various business data, including environmental monitoring, equipment state monitoring and fault early warning information;
and simulating the operation performance of the fan under different wind speed conditions through a digital twin model, evaluating the effect of a maintenance strategy, and predicting the equipment fault risk.
In a second aspect, an embodiment of the present application provides a digital twin-based wind farm equipment modeling and operation and maintenance control device, which is applied to the digital twin-based wind farm equipment modeling and operation and maintenance control method according to the first aspect, and the device includes:
The high-precision digital twin model construction module is used for restoring a fan entity based on a 1:1 three-dimensional modeling technology, integrating multi-source data to realize real-time mapping of a physical field and a virtual field, and constructing a high-precision digital twin model, wherein the multi-source data comprises a device sensor, video monitoring and GIS topography;
the intelligent decision support module predicts wind resource distribution by utilizing a dynamic boundary layer model, optimizes a grid-connected control strategy by combining a virtual inertia simulation technology, carries out intelligent decision support and realizes the guarantee of transient stability of the power grid under a new energy fluctuation scene;
and the full life cycle management platform is constructed, and full flow management from site selection planning, operation monitoring to fault diagnosis is realized through a three-dimensional visual large screen, so that multi-service data fusion display and interactive operation and maintenance strategy verification are realized.
In a third aspect, an embodiment of the present application provides an electronic device, including:
A processor;
a memory for storing processor-executable instructions;
the processor is configured to implement the digital twin-based wind farm equipment modeling and operation and maintenance control method according to the first aspect when executing the instructions.
In a fourth aspect, an embodiment of the present application provides a computer readable storage medium, where a program is stored, the program instructs a device to perform a method for modeling and controlling operation of a wind farm device based on digital twinning according to the first aspect.
The beneficial effects of this scheme include specifically:
(1) And (3) constructing a high-precision digital twin model, namely restoring a fan entity based on a 1:1 three-dimensional modeling technology, integrating multi-source data (equipment sensors, video monitoring and GIS topography) and realizing real-time mapping of a physical field and a virtual field.
(2) And the intelligent decision support module predicts wind resource distribution by utilizing a dynamic boundary layer model, optimizes a grid-connected control strategy by combining a virtual inertia simulation technology, and realizes the guarantee of transient stability of the power grid under the new energy fluctuation scene.
(3) And the full life cycle management platform supports full-flow management from site selection planning, operation monitoring and fault diagnosis, and realizes multi-service data fusion display and interactive operation and maintenance strategy verification through a three-dimensional visual large screen.
Drawings
Fig. 1 is a schematic flow chart of a digital twin-based wind farm equipment modeling and operation and maintenance control method according to an embodiment of the present application.
Fig. 2 is a schematic three-dimensional modeling diagram of a general wind turbine according to an embodiment of the present application.
Fig. 3 is a schematic diagram of a digital twin-based wind farm equipment modeling and operation management and control device according to an embodiment of the present application.
Fig. 4 is a schematic diagram of an electronic terminal device according to an embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the present application.
It should be noted that, in the embodiments of the present application, "at least one" refers to one or more, and a plurality refers to two or more. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.
It should be noted that, in the embodiments of the present application, the terms "first," "second," and the like are used for distinguishing between the descriptions and not necessarily for indicating or implying a relative importance, or for indicating or implying a sequence. Features defining "first", "second" may include one or more of the stated features, either explicitly or implicitly. In describing embodiments of the present application, words such as "exemplary" or "such as" are used to mean serving as examples, illustrations, or descriptions. Any embodiment or design described herein as "exemplary" or "e.g." in an embodiment should not be taken as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion.
All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without any inventive effort, are intended to be within the scope of the present application.
In view of the above, the application provides a method and a device for modeling and operation and maintenance control of wind power plant equipment based on digital twinning, which are constructed by a high-precision digital twinning model, wherein a fan entity is restored based on a 1:1 three-dimensional modeling technology, and real-time mapping of a physical field and a virtual field is realized by integrating multi-source data (equipment sensors, video monitoring and GIS topography). And the intelligent decision support module predicts wind resource distribution by utilizing a dynamic boundary layer model, optimizes a grid-connected control strategy by combining a virtual inertia simulation technology, and realizes the guarantee of transient stability of the power grid under the new energy fluctuation scene. And the full life cycle management platform supports full-flow management from site selection planning, operation monitoring and fault diagnosis, and realizes multi-service data fusion display and interactive operation and maintenance strategy verification through a three-dimensional visual large screen.
Fig. 1 is a schematic flow chart of a digital twin-based wind farm equipment modeling and operation and maintenance control method according to an embodiment of the present application.
And 1, restoring a fan entity based on a 1:1 three-dimensional modeling technology, integrating multi-source data to realize real-time mapping of a physical field and a virtual field, and constructing a high-precision digital twin model, wherein the multi-source data comprises equipment sensors, video monitoring and GIS topography.
Specifically, in the embodiment of the application, the fan entity is restored based on a 1:1 three-dimensional modeling technology, the real-time mapping of a physical field and a virtual field is realized by integrating multi-source data, and a digital twin model of a high-precision wind turbine generator is constructed, wherein the digital twin model consists of four parts, namely, construction of a geometric model, construction of a mechanism model, construction of a data model and construction of a knowledge model;
the construction of the geometric model comprises the steps of constructing a three-dimensional geometric model of a 1:1 wind turbine by three-dimensional modeling software and field measurement data, and restoring the three-dimensional space environment of a real wind turbine by three-dimensional surface information of a blade, a tower and a gear box part to realize high-precision geometric modeling;
The construction of the mechanism model comprises the steps of simulating mechanical behaviors of a blade and a tower by using a finite element analysis model, establishing a thermodynamic model and a vibration model of the wind turbine based on energy conservation and momentum conservation laws, constructing a control strategy based on a physical mechanism, including a wake effect model and a variable pitch control strategy, so as to optimize the power generation efficiency, establishing an electrical system, a mechanical structure and an aerodynamic model of the wind turbine, and simulating the running state and dynamic response of the wind turbine;
The data model is constructed by acquiring key parameters of wind speed, wind direction, power and temperature in real time through an S C A D A system and a state monitoring system, and inputting the key parameters into the model for dynamic simulation;
The knowledge model is constructed by establishing a knowledge graph of the relation between the running state and the fault of the wind turbine, and carrying out intelligent prediction and fault diagnosis on the running state of the wind turbine by combining a machine learning algorithm.
Fig. 2 is a schematic three-dimensional modeling diagram of a general wind turbine according to an embodiment of the present application. In particular, the first part of the digital twin model is the construction of the geometric model. Three-dimensional space environment of the wind turbine generator, including three-dimensional surface information of components such as blades, towers, gearboxes and the like, can be accurately restored through three-dimensional modeling software (such as Ble n d e r, ma y a and the like) and field measurement data. The method can realize high-precision geometric modeling and provide basic support for subsequent simulation and analysis. In addition, the three-dimensional modeling technology can also present the actual scene in a three-dimensional model form, so that visual display of the virtual reality is realized.
The second part of the digital twin model is the construction of the mechanism model. The method is mainly based on a physical mechanism, and a thermodynamic model and a vibration model are established by simulating the mechanical behaviors of the blade and the tower through a finite element analysis model. Meanwhile, an electric system, a mechanical structure and an aerodynamic model of the wind turbine generator are constructed by combining energy conservation and momentum conservation law, and the running state and dynamic response of the wind turbine generator are simulated. In addition, control strategies based on physical mechanisms, such as wake effect models and pitch control strategies, are included to optimize the power generation efficiency.
The data model is one of the core parts of the digital twin system. And acquiring key parameters such as wind speed, wind direction, power, temperature and the like in real time through an S C A D A system and a state monitoring system, and inputting the data into a model for dynamic simulation. The data driving model trains a neural network through historical data and optimizes the model prediction precision, so that the accurate prediction and fault diagnosis of the running state of the wind turbine generator are realized.
Knowledge models are another important component of digital twinning systems. And intelligent prediction and fault diagnosis are carried out on the running state of the wind turbine by establishing a knowledge graph of the relation between the running state of the wind turbine and the fault and combining a machine learning algorithm. For example, by utilizing a multi-factor fusion analysis technology, the fan design, the operation and maintenance mode and the fault data can be comprehensively analyzed, so that accurate state monitoring and prediction are realized.
The overall architecture of the digital twin model includes an organic combination of a geometric model, a mechanism model, a data model, and a knowledge model. The architecture can realize seamless mapping of physical entities and virtual digital space and support real-time simulation deduction. For example, in wind power plant management, the digital twin system can help a manager to master the running state of a wind turbine through real-time monitoring and early warning functions, optimize maintenance plans and improve power generation efficiency
The construction of the digital twin model of the high-precision wind turbine generator further comprises the following steps:
From the system dimension of the wind power plant, the operation requirement is disassembled into six important dimensions of man, machine, material, method, ring and measurement, the digital twin body is constructed for the environment, equipment, personnel and management flow, and the operation and the scheduling of loading, cooperation and fusion are carried out on the multiple twin bodies through digital threads, so that the actual business requirement of the operation and the maintenance of the wind power plant is reflected to the greatest extent, and the comprehensive digital management of the wind power plant is realized;
by constructing a three-dimensional model of the wind field environment based on the IF C standard and an internal power generation process of a fan system, organically combining the 3D GIS, BIM information and the fan C A D model, and establishing comprehensive production perceptibility in a virtual space;
based on the comprehensive analysis of the fan design data, the operation and maintenance data and the fault mode, adopting a targeted twin body modeling method for different components,
The state monitoring, fault prediction and simulation deduction of the generator winding are completed through the constructed hybrid model, and the self-learning and continuous optimization of the model structure and parameters can be performed by utilizing the operation data collected in real time.
The dimensional resolution and modeling elements of the six-dimensional digital twin construct are shown in the following table:
from the system dimension of the wind power plant, the operation requirements are disassembled to six important dimensions of man, machine, material, method, ring and survey, and a digital twin body of an environment, equipment, personnel and management flow is constructed through a digital twin technology, so that the method is a key path for realizing comprehensive digital management of the wind power plant.
The digital twin technology can clearly show the operation flow and the working rule of the wind power plant staff through a three-dimensional model and a virtual space. For example, by combining BIM information and a C A D model through a three-dimensional model based on an IF C standard, a worker can intuitively grasp the power generation rule and adjust operation in time, so that risks caused by improper operation and maintenance activities are avoided. In addition, the intelligent inspection technology (such as image recognition, infrared imaging and the like) can reduce the workload of field personnel and improve the operation and maintenance efficiency.
The digital twin body of the wind power plant equipment can realize the real-time monitoring of the full life cycle of equipment state, structure, production, faults and the like. For example, a digital twin platform may demonstrate a digitized representation of the blower structure and operating mechanism through a sensor data acquisition and monitoring system. Meanwhile, the wind power digital twin system based on hybrid modeling can model generator winding state monitoring, fault prediction and simulation deduction, and reliability and operation and maintenance efficiency of equipment are improved.
The material (material) digital twin technology can optimize the material use and management of the wind power plant. For example, in wind field layout optimization, the fan layout is reasonably planned by simulating different topography and wind speed characteristics, so that material waste is reduced and resource utilization rate is improved.
The digital twin technology can be combined with big data analysis and wind power model simulation technology to quantitatively analyze various indexes in the operation process, so that scientific basis is provided for the operation management of the wind power plant. In addition, through the knowledge base of standardized auxiliary solutions, standardized management of operation and maintenance flows can be realized.
The digital twin technology can monitor the environmental data of the wind power plant in real time, such as meteorological conditions, wind speed changes and the like, and early warn the potential risk in advance through a prediction model. For example, the marine weather auxiliary support system may monitor the strong weather process of the offshore wind farm in real time and forecast future weather conditions.
The digital twin technology can comprehensively monitor the running state of the wind power plant through multi-source data fusion and real-time simulation deduction. For example, through the edge computing node layer and the public and private cloud cooperation layer, prediction and diagnosis of faults of wind turbine generator equipment can be achieved. In addition, the intelligent collaborative management and control technology for wind power construction based on digital twinning can realize the omnibearing sensing and management of construction information.
The actual business requirements of the wind power plant operation and maintenance can be reflected to the greatest extent through loading, cooperation and fusion operation and scheduling of the multiple twin bodies by the digital threads. For example, the digital twin-based wind farm operation management platform can realize the digital, centralized and remote upgrading of management work of almost all links.
The comprehensive digital management of the wind power plant needs to construct digital twin bodies of six dimensions of people, machines, materials, methods, rings and survey through digital twin technology, and the cooperation and fusion of multiple twin bodies are realized through digital threads. The method not only can improve the operation and maintenance efficiency and safety of the wind power plant, but also can provide powerful technical support for sustainable development of the wind power industry.
And 2, predicting wind resource distribution by utilizing a dynamic boundary layer model, optimizing a grid-connected control strategy by combining a virtual inertia simulation technology, and carrying out intelligent decision support to realize the guarantee of the transient stability of the power grid under the new energy fluctuation scene.
Specifically, in the embodiment of the present application, the method for predicting wind resource distribution by using a dynamic boundary layer model and optimizing a grid-connected control strategy by combining a virtual inertia simulation technology to perform intelligent decision support, so as to realize the guarantee of transient stability of a power grid under a new energy fluctuation scene, includes:
constructing a dynamic boundary layer model through input data, wherein the input data comprises topographic data, meteorological data and thermodynamic data;
According to the space-time evolution of wind speed in the description atmosphere boundary layer, a momentum equation is constructed, and the formula is as follows:
u i、uj denotes the wind speed component, x i、xj denotes the component of the corresponding parameter, i, j=1, 2,3, ρ denotes the air density, p denotes the air pressure, f c denotes the coriolis parameter, τ ij denotes the reynolds stress, S i denotes the source term, ζ ijk denotes the complete antisymmetric tensor;
Predicting the space-time distribution characteristic of wind resources according to the dynamic boundary layer model;
according to the virtual inertia compensation target, the grid-connected control strategy is optimized by combining the virtual inertia simulation technology, the virtual inertia is optimally distributed, the stable power grid frequency is maintained, and the virtual inertia compensation target formula is as follows:
Wherein, H rcof,HΔf represents critical virtual inertia obtained under different constraint conditions, S gi represents rated capacity of the ith wind turbine generator, S wfj represents rated capacity of the jth generator wind farm, H gi represents inertia of the ith wind turbine generator, m represents number of wind turbine generator, and n represents number of wind farms with virtual inertia.
In the embodiment of the application, wind resource distribution is predicted through a dynamic boundary layer model, and a grid-connected control strategy is optimized by combining a virtual inertia simulation technology, so that the aim of ensuring the transient stability of the power grid under the new energy fluctuation scene is fulfilled.
Based on the dynamic boundary layer model, the space-time distribution characteristic of wind resources can be predicted. This step provides basic data support for subsequent virtual inertia optimization assignments. For example, the wind speed fluctuation characteristics of the wind farm can be obtained through model analysis, so that basis is provided for scheduling and controlling the wind farm.
The optimizing distribution of the virtual inertia, maintaining the stable frequency of the power grid, comprises the following steps:
Adopting a self-adaptive control algorithm to realize accurate control and smooth adjustment of the output power of the wind power plant;
wherein, the self-adaptive rule is as follows:
Monitoring the running state data of the wind turbine, comparing the running state data with a preset threshold value, starting virtual inertia to control when the deviation exceeds the data range of the threshold value, the method comprises the steps of adjusting the rotating speed or power output of a wind turbine generator, providing additional inertial support for a power grid, slowing down the speed of frequency change, and striving for time for frequency modulation measures, wherein the running state data comprise working frequency and fan rotating speed;
Setting a virtual inertia control time threshold, and stopping controlling the virtual inertia when the running state data of the wind turbine generator is recovered, or stopping controlling the virtual inertia when the control time reaches the control time threshold.
And monitoring running state data, namely monitoring running state data such as the working frequency, the fan rotating speed and the like of the wind turbine generator in real time, and comparing the running state data with a preset threshold value. When the deviation exceeds the threshold range, virtual inertia control is started, the rotation speed or power output of the wind turbine generator is adjusted, additional inertial support is provided for the power grid, the speed of frequency change is slowed down, and time is strived for frequency modulation measures. And setting a virtual inertia control time threshold value, namely stopping controlling the virtual inertia when the running state data of the wind turbine generator is restored to a normal range, or stopping controlling the virtual inertia when the control time reaches a preset time threshold value.
The virtual inertia compensates for the active power shortage by releasing the kinetic energy stored in the wind generating set rotating system, thereby providing short-time rotational inertia support for the power grid. The control mode can quickly respond when the frequency of the power grid changes rapidly, slow down the frequency fluctuation and strive for time for frequency modulation measures. For example, virtual inertia control can significantly improve the frequency dynamic response of a wind farm in grid-tie conditions within 0.5 seconds after a frequency disturbance.
Through the self-adaptive control algorithm, the accurate control and smooth adjustment of the output power of the wind power plant are realized. The method is characterized in that control parameters of virtual inertia are dynamically adjusted according to running state data of the wind turbine generator, so that frequency response characteristics are optimized. For example, the fan virtual inertia optimization control strategy based on the parameter fuzzy reasoning can avoid the contradiction between the inherent speed controller and the virtual inertia control link by dynamically adjusting the virtual inertia control parameter, thereby remarkably improving the frequency modulation performance and improving the frequency stability of the system.
In actual operation, the virtual inertia control parameters are dynamically adjusted according to the wind speed change so as to adapt to the real-time wind speed change and compensate for grid inertia weakening caused by wind power integration. For example, when a frequency disturbance occurs, the control parameters are quickly adjusted to achieve virtual inertia compensation.
According to the method, through the self-adaptive control algorithm and dynamic adjustment of virtual inertia, accurate control and smooth adjustment of output power of the wind power plant are achieved, and stability of power grid frequency is effectively improved. The method not only can cope with frequency disturbance, but also can further improve the robustness and adaptability of the system by optimizing the allocation strategy. And 3, constructing a full life cycle management platform, carrying out full-flow management from site selection planning, operation monitoring and fault diagnosis, and realizing multi-service data fusion display and interactive operation and maintenance strategy verification through a three-dimensional visual large screen.
Specifically, in the embodiment of the present application, the building of the full life cycle management platform, the full process management from site selection planning, operation monitoring to fault diagnosis, includes:
Through the whole life cycle of the wind power plant equipment, mapping the whole flow from site selection planning and operation monitoring to fault diagnosis is carried out by a digital twin technology, the overall layout of the wind power plant and the monitoring of the equipment state are carried out by a three-dimensional visual platform, and the site selection planning and construction scheme is optimized;
and by combining GIS and BIM technologies, the geographic information and equipment information of the wind power plant are integrally managed, so that the whole flow digital management and control from site selection to operation and maintenance is realized.
The realization of multi-service data fusion display and interactive operation and maintenance strategy verification through the three-dimensional visual large screen comprises the following steps:
The three-dimensional visual large screen is used for displaying key indexes of the generated energy, the power and the wind speed of the wind turbine generator in real time, and combining an unmanned aerial vehicle oblique photography technology, dynamically feeding back the health condition of the blade, and carrying out fusion analysis of various business data, including environmental monitoring, equipment state monitoring and fault early warning information;
and simulating the operation performance of the fan under different wind speed conditions through a digital twin model, evaluating the effect of a maintenance strategy, and predicting the equipment fault risk.
The digital twin technology has significant advantages in wind farm site selection planning. Through simulating different topography (such as mountain land, plain, coast) and wind speed, wind direction characteristic that corresponds, can rationally plan fan overall arrangement, consider electric wire netting access point's position and transmission line trend simultaneously, overall arrangement infrastructure construction in advance ensures the security and the economic nature of electric power transmission. In addition, the GIS is used as a data space integrated bottom plate and combined with the BIM model, so that the optimization of wind power plant microcosmic site selection can be realized, and site selection accuracy is further improved through loading basic remote sensing data, oblique photography and laser point cloud data through a three-dimensional scene.
The digital twin technology maps wind power plant equipment and environmental parameters into a virtual model in real time through a three-dimensional visual platform, so that the monitoring of the overall layout and equipment state of the wind power plant is realized. For example, by using the unmanned aerial vehicle oblique photography technology to feed back the running state of the blade in real time, a manager can grasp the change trend of the generated energy at any time and adjust the operation and maintenance activities. In addition, the three-dimensional visualization system can also display environmental parameters such as wind speed, wind direction, temperature and the like, and the inspection efficiency and accuracy are improved through the intelligent inspection function.
Fig. 3 is a schematic diagram of a digital twin-based wind farm equipment modeling and operation management and control device according to an embodiment of the present application. The device for modeling and controlling operation and maintenance of wind power plant equipment based on digital twin as shown in fig. 3 comprises a high-precision digital twin model construction module 11, an intelligent decision support module 12 and a full life cycle management platform 13 which are sequentially connected, wherein:
it can be understood that the high-precision digital twin model construction module 11 restores the fan entity based on a 1:1 three-dimensional modeling technology, integrates multi-source data to realize real-time mapping of a physical field and a virtual field, and constructs a high-precision digital twin model, wherein the multi-source data comprises equipment sensors, video monitoring and GIS topography.
It can be understood that the intelligent decision support module 12 utilizes the dynamic boundary layer model to predict wind resource distribution, combines the virtual inertia simulation technology to optimize the grid-connected control strategy, carries out intelligent decision support, and realizes the power grid transient stability guarantee under the new energy fluctuation scene.
It can be understood that the full life cycle management platform 13 is constructed, and the full-flow management from site selection planning, operation monitoring to fault diagnosis is realized through the three-dimensional visual large screen to realize multi-service data fusion display and interactive operation and maintenance strategy verification.
Referring to fig. 4, fig. 4 is an electronic terminal device 4 according to an embodiment of the present application. The electronic terminal device shown in fig. 4 comprises at least a processor 101 and a memory 100, a communication interface 103, and a bus 102. In an embodiment of the present application, the memory 100 is used for storing instructions executable by the processor 101, and the processor 101 is configured to implement the method as shown in fig. 1 when executing the instructions. The processor, the input device, the output device and the memory complete communication with each other through a communication bus. The memory is for storing a computer program comprising program instructions. The processor is configured to execute the program instructions stored in the memory. Wherein the processor is configured to invoke program instructions to perform the following functions of the modules/units in the above-described device embodiments, such as the functions of the modules shown in fig. 3.
In an embodiment of the application, a computer-readable storage medium includes instructions that instruct a device to perform a system as in the first aspect. For example, the instruction instructs the device to perform a digital twin based wind farm device modeling and operation management method, apparatus as shown in the steps of fig. 1.
It should be appreciated that in embodiments of the present invention, the processor may be a central processing unit (CE N T R ALPR o C e S sin G U nit, cpeu), other general purpose processors, digital signal processors (DIGIT ALSIG N ALPR oc S S o r, dsp), application specific integrated circuits (A P plic a tio N S P E CIFICIN T E G R A T E D CIR C uit, asic), off-the-shelf programmable gate arrays (Field-Pr o G r a m m a ble GA T E AR R A Y, fpga) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The electronic device according to the above embodiment is also partially implemented by a computer. In this case, the program for realizing the control function may be recorded on a computer-readable recording medium, and the program recorded on the recording medium may be read into a computer and executed.
The input device may include a touch pad, a fingerprint sensor (for collecting fingerprint information of a user and direction information of a fingerprint), a microphone, etc., and the output device may include a display (L C D, etc.), a speaker, etc.
The term "computer" as used herein refers to a computer built into an electronic device, and a computer including O S and peripheral devices is used. The "computer-readable recording medium" refers to a removable medium such as a floppy disk, a magneto-optical disk, or an rθm, C D —rθm, or a storage device such as a hard disk incorporated in a computer.
The "computer-readable recording medium" may include a medium that dynamically stores a program in a short time, such as a communication line when the program is transmitted via a network such as the internet or a communication line such as a telephone line, or a medium that stores the program in a fixed time, such as a volatile memory in a computer that is a server or a client in this case. The program may be a program for realizing a part of the functions described above, or may be a program capable of realizing the functions described above by being combined with a program recorded in a computer.
The electronic apparatus according to the above embodiment may be realized as an aggregate (device group) including a plurality of devices. Each device constituting the device group may include a part or all of each function or each functional block of the electronic apparatus according to the above embodiment. The device group may have all the functions or functional blocks of the electronic apparatus.
It will be appreciated by persons skilled in the art that the above embodiments have been provided for the purpose of illustrating the application and are not to be construed as limiting the application, and that suitable modifications and variations of the above embodiments are within the scope of the application as claimed.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510467941.4A CN120389511A (en) | 2025-04-15 | 2025-04-15 | A wind farm equipment modeling and operation and maintenance control method and device based on digital twin |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510467941.4A CN120389511A (en) | 2025-04-15 | 2025-04-15 | A wind farm equipment modeling and operation and maintenance control method and device based on digital twin |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN120389511A true CN120389511A (en) | 2025-07-29 |
Family
ID=96492601
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510467941.4A Pending CN120389511A (en) | 2025-04-15 | 2025-04-15 | A wind farm equipment modeling and operation and maintenance control method and device based on digital twin |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120389511A (en) |
-
2025
- 2025-04-15 CN CN202510467941.4A patent/CN120389511A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115013261B (en) | State monitoring method and system for offshore wind farm | |
| CN113236491A (en) | Wind power generation digital twin system | |
| CN108027908B (en) | Simulation method and system | |
| CN114567072B (en) | Control system of photovoltaic power station | |
| CN110147931A (en) | Intelligent panoramic system and intelligent panoramic power grid | |
| CN111525684A (en) | Operation and maintenance system for wind power plant clustering monitoring based on cloud platform | |
| CN112329977A (en) | Wind power prediction system for extreme scene | |
| CN107967599A (en) | A kind of Wind Power Project development system and development approach based on exploitation map | |
| CN118487276A (en) | A method and system for dynamic control of power grid security for power security objects | |
| Sayed et al. | Wind power plants control systems based on SCADA system | |
| Zhang et al. | Digital twin in energy internet and its potential applications | |
| CN120110008A (en) | A three-dimensional digital intelligent monitoring system suitable for photovoltaic power stations | |
| KR20200084108A (en) | System for supporting a decision making for wind turbine o&m | |
| Chen et al. | RETRACTED ARTICLE: Thermal power generation fault diagnosis and prediction model based on deep learning and multimedia systems | |
| Kanimozhi et al. | Intelligent Transportation Systems: Exploring Digital Twin Technologies in Smart Grid, Transportation Systems and Smart Cities | |
| CN119066976A (en) | A wind farm three-dimensional modeling data visualization analysis method and related device | |
| CN119377913A (en) | Wind turbine generator generation capacity analysis, diagnosis and optimization method and device | |
| US8407111B2 (en) | Method, system and computer program product for correlating information and location | |
| CN120389511A (en) | A wind farm equipment modeling and operation and maintenance control method and device based on digital twin | |
| CN111259570B (en) | A method for quantification of wind farm active power reserve based on information physics system | |
| CN118154157A (en) | Wind power operation and maintenance platform based on big data | |
| CN117892253A (en) | An intelligent ship system based on multi-source data fusion | |
| Kunzemann et al. | Application of CPS within wind energy—current implementation and future potential | |
| Yu et al. | Research on application of information model in wind turbine fault diagnosis | |
| Zhang et al. | Research and practice on the intelligent photovoltaic power station in Yalong River Basin |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |